Peter Elmers, Hongyu Li, Shams Imam, Vivek Sarkar
2014 Proceedings of the companion publication of the 2014 ACM SIGPLAN conference on Systems, Programming, and Applications: Software for Humanity - SPLASH '14  
Motivation The proliferation of multicore processors warrants parallelism as the future of computing, increasing the demand to write parallel programs for increased application performance. Previous experience has shown that writing explicitly parallel programs is inherently more difficult than writing sequential programs. Programmers need parallel programming models, constructs, and tools that can simplify writing of parallel programs. In this poster, we present an innovative new tool, HJ-Viz,
more » ... which generates interactive Computation Graphs (CGs) of parallel programs by analyzing event logs. The visual feedback is valuable for a programmer to efficiently optimize program logic and to eliminate the presence of potential bugs which may otherwise be difficult to detect. For example, in cases of deadlocks, HJ-Viz enables users to visualize and easily diagnose the deadlock scenario. CGs provide an intuitive graphical view of a parallel program's execution. A CG is an acyclic graph that consists of: a) a set of nodes, where each node represents a step consisting of sequential computation, and b) a set of directed edges that represent ordering constraints among steps. A task can be partitioned into multiple steps, the key constraint is that a step should not contain any parallelism or synchronization. We incorporate Abstract Execution Metrics (AEM) as well as Real Time Metrics (RTM) in the visualization. AEM describe the performance of a program by measuring the cost of abstract operations, such as floating-point, comparison, stencil, or data structure operations. RTM inserts timing calls to record the time elapsed between consecutive synchronization events. Programmers can use the visualization of the CG by HJ-Viz to pinpoint potential sources of bugs and points of im-Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored.
doi:10.1145/2660252.2660395 dblp:conf/oopsla/ElmersLIS14 fatcat:uhsjufrc25bbxjovbowzw4cnoy